Instructions to use SystemAdmin123/tiny-random-LlamaForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SystemAdmin123/tiny-random-LlamaForCausalLM with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SystemAdmin123/tiny-random-LlamaForCausalLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SystemAdmin123/tiny-random-LlamaForCausalLM")
model = AutoModelForCausalLM.from_pretrained("SystemAdmin123/tiny-random-LlamaForCausalLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SystemAdmin123/tiny-random-LlamaForCausalLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SystemAdmin123/tiny-random-LlamaForCausalLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SystemAdmin123/tiny-random-LlamaForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SystemAdmin123/tiny-random-LlamaForCausalLM

SGLang

How to use SystemAdmin123/tiny-random-LlamaForCausalLM with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SystemAdmin123/tiny-random-LlamaForCausalLM" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SystemAdmin123/tiny-random-LlamaForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SystemAdmin123/tiny-random-LlamaForCausalLM" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SystemAdmin123/tiny-random-LlamaForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SystemAdmin123/tiny-random-LlamaForCausalLM with Docker Model Runner:
```
docker model run hf.co/SystemAdmin123/tiny-random-LlamaForCausalLM
```

SystemAdmin123 commited on Feb 7, 2025

Commit

7e50d19

verified ·

1 Parent(s): 7e389f9

Training in progress, step 60, checkpoint

Browse files

Files changed (8) hide show

last-checkpoint/model.safetensors +1 -1
last-checkpoint/optimizer.pt +1 -1
last-checkpoint/rng_state_0.pth +1 -1
last-checkpoint/rng_state_1.pth +1 -1
last-checkpoint/rng_state_2.pth +1 -1
last-checkpoint/rng_state_3.pth +1 -1
last-checkpoint/scheduler.pt +1 -1
last-checkpoint/trainer_state.json +25 -3

last-checkpoint/model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94661efade50fe6aebdc27ba404c3ae586977e95a0a5743328cfd154ad1fc910
 size 2066752

 version https://git-lfs.github.com/spec/v1
+oid sha256:155968869fcca097b33aaf908240b52fd8118e8fa88db2b3c2604bacade85ac1
 size 2066752

last-checkpoint/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed634c87695c3354020e98afbf649d6ef58b6c85d097e57430eb83fe04ceb0eb
 size 2162798

 version https://git-lfs.github.com/spec/v1
+oid sha256:50397b505bb135379928c86c3229e296d07221c0a9051ba1a7a679e11bada8c3
 size 2162798

last-checkpoint/rng_state_0.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9d8ba6dc294a7802a4dafc0e564c1a2eee3305104ad939fbc56d5ce507ea444
 size 15024

 version https://git-lfs.github.com/spec/v1
+oid sha256:55dcddf95f6df626baaef418beac8e8ae2cf66b3e94fecb344f33442737e8951
 size 15024

last-checkpoint/rng_state_1.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0cceb0ed85b2c6f37fd08e1761f95ce6ce00ab47aa275d076d6aa53a386d4e
 size 15024

 version https://git-lfs.github.com/spec/v1
+oid sha256:a64d4aece2607f1d3bc7ea4374d4260437623a49135c05801f0d688b2e80f254
 size 15024

last-checkpoint/rng_state_2.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2204e8c1dd9dc7722a4f81e5fd4492d8dfa53c90fc9556f23dafd200a539a7a
 size 15024

 version https://git-lfs.github.com/spec/v1
+oid sha256:34c21f77637fb3f56ba02ef509b8a471991cc2ccccca6af51847140ee757415a
 size 15024

last-checkpoint/rng_state_3.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9003a850e509d15b02ef8ebe5e4de4ee92eba098365621434af147786d9f58d1
 size 15024

 version https://git-lfs.github.com/spec/v1
+oid sha256:a6687608b07c4a2d2152b65f49fc8bc54d8b4fc77151984b62a1a90d271ed6a0
 size 15024

last-checkpoint/scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02fba4d221acb6fea331334b3de1974a87e216e52fc96554556bafda3bca4247
 size 1064

 version https://git-lfs.github.com/spec/v1
+oid sha256:f299ab56b5f200cab03608b3ac75cf1761ca29c2207c1dfe5ab919b66f8dbd88
 size 1064

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.666666666666667,
   "eval_steps": 20,
-  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 646.597,
       "eval_steps_per_second": 5.169,
       "step": 40
     }
   ],
   "logging_steps": 10,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 32732683960320.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

 {
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 10.0,
   "eval_steps": 20,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "eval_samples_per_second": 646.597,
       "eval_steps_per_second": 5.169,
       "step": 40
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 10.2602,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.326171875,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 10.2203,
+      "step": 60
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 10.208223342895508,
+      "eval_runtime": 2.3491,
+      "eval_samples_per_second": 638.981,
+      "eval_steps_per_second": 5.108,
+      "step": 60
     }
   ],
   "logging_steps": 10,
       "attributes": {}
     }
   },
+  "total_flos": 49099025940480.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null